A new and improved strategy for detecting cyberattacks on manufacturing systems involves using AI to monitor a digital twin that mimics and is fed real-time data from the physical system.
Cybersecurity has long been a cat-and-mouse game between enterprises and hackers — or, more benignly, between enterprises and the mistakes their own people tend to make. Now, there is potential for essential operations and data to be separated from vulnerable surfaces, through digital twins technology.
That’s the word from the National Institute of Standards, which highlights a paper published in IEEE Transactions on Automation Science and Engineering, in which NIST and University of Michigan researchers demonstrated the feasibility of a digital-twin cybersecurity strategy by detecting cyberattacks aimed at a 3D printer in their lab. This is a framework that is applicable to could be applied to a broad range of commercial settings, and invokes new analytic capabilities. “A new and improved strategy for detecting cyberattacks on manufacturing systems, such as 3D printers, involves using AI to monitor a digital twin that mimics and is fed real-time data from the physical system,” according to the NIST authors.
Employing digital twin technology to sense abnormalities or intrusions has long been hampred by the impact that detecting cyberattacks has had the impact on system performance. Systems may need to be shut down to enable tools or administrators to probe for security information. “Operational data describing what is occurring within machines — sensor data, error signals, digital commands being issued or executed, for instance — could support cyberattack detection.,” according to the NIST paper. “However, directly accessing this kind of data in near real time from operational technology devices, such as a 3D printer, could put the performance and safety of the process on the factory floor at risk.”
Security data is inherent within digital twin platforms. Typically, they incorporate “an abundance of operational data, helping them accomplish a variety of feats without impacting performance or safety, including predicting when parts will start to break down and require maintenance,” the NIST authors relate. “In addition to spotting routine indicators of wear and tear, digital twins could help find something more within manufacturing data.”
“Because manufacturing processes produce such rich data sets — temperature, voltage, current — and they are so repetitive, there are opportunities to detect anomalies that stick out, including cyberattacks,” said Dawn Tilbury, a professor of mechanical engineering at the University of Michigan and study co-author.
In Tilbury’s demonstration project, the models incorporated into the digital twin “were adept at recognizing what the printer looked like under normal conditions, also meaning they could tell when things were out of the ordinary. If these models detected an irregularity, they passed the baton off to other computer models that checked whether the strange signals were consistent with anything in a library of known issues, such as the printer’s fan cooling its printing head more than expected. Then the system categorized the irregularity as an expected anomaly or a potential cyber threat.” A human expert made the final call as to whether the security threat was valid.
“If the framework hasn’t seen a certain anomaly before, a subject matter expert can analyze the collected data to provide further insights to be integrated into and improve the system,” said lead-author Efe Balta, a postdoctoral researcher at ETH Zurich. In the process, the model would learn what constitutes potential cybersecurity threats.
So far, so good: Where AI is mature, business success follows.
getty
It’s too early to tell if artificial intelligence (AI) will deliver on all the hype and promises around it. But in the meantime, the results we do see trickling in are encouraging. A survey just released shows that the majority of organizations that use AI are still experimenting with the technology, with about 12% have the technology truly at work in a fully “mature” fashion. The mature AI sites notably are seeing strong competitive advantage.
The study from Accenture, which covered of 1,176 firms and 1,615 executives across the globe, estimates that the number of fully mature AI initiatives is projected to increase from 12% to 27% over the next two years. At this point, a majority, 63%, are still mostly testing the waters.
The 12% who have mastered AI already are seeing 50% greater revenue growth on average compared with their peers, according to the study’s team of authors — led by Accenture’s Sanjeev Vohra. They assembled another interesting metric: among executives of the world’s 2,000 largest companies (by market capitalization), those who discussed AI on their 2021 earnings calls were 40% more likely to see their firms’ share prices increase—up from 23% in 2018. Companies leading the way are already seeing the results—42% said that the return on their AI initiatives exceeded their expectations, while only 1% said the return didn’t meet expectations.
Vohra and his co-authors define AI maturity as “the degree to which organizations outperform their peers in a combination of AI-related foundational and differentiating capabilities. These capabilities include the technology – data, AI, cloud – as well as organizational strategy, responsible AI, C-suite sponsorship, talent and culture.”
The report explores what members of that elite 12% — the mature AI achievers — do differently, and it goes well beyond technology implementations. Along with the science of AI, “our findings demonstrate there is also an art to AI maturity,” the Accenture authors state. “Achievers are not defined by the sophistication of any one capability, but by their ability to combine strengths across strategy, processes and people.”
MORE FOR YOU
Here are five ways “AI Achievers” master their craft, as found in the research:
Enthusiastic support from the C-suite: This is essential, as AI initiatives compete with other initiatives for attention and resources. More than eight in ten, 83%, of AI Achievers have executives sponsorship, compared of experimenters. “Our research also suggests that the best AI strategies tend to be bold, even when they have modest beginnings,” according to Vohra and his co-authors. “Bold AI strategies, in turn, help spur innovation.”
Heavy investments in talent and training: AI Achievers “are more likely to invest heavily in creating data and AI fluency across their workforces,” the Accenture analysts point out. “We found that 78% of AI achievers—compared with just 51% of experimenters—have mandatory AI trainings for most employees, from product development engineers to C-suite executives. Nearly half (44%) of achievers have employees with consistently high AI skills competencies, while experimenters (30%) have significantly fewer such employees, on average.”
They think in terms of “platform”: Call it industrialization, built on trustworthy data flowing in and out. AI achievers seek to build “an operational data and AI platform that taps into companies’ talent, technology and data ecosystems, allowing firms to balance experimentation and execution.” This serves to help “productize their AI applications and integrate AI into other applications.”
They design AI responsibly, from the start: Increasingly, AI may need to adapt to laws, regulations and ethical norms. AI achievers are 53% more likely, on average, than their less-mature counterparts “to be responsible by design: designing, developing and deploying AI with good intention to empower employees and businesses, and to fairly impact customers and society.”
They prioritize long- and short-term AI investments. AI achievers get more out of AI “simply because they invest more in it,” Vohra and his co-authors state. In 2018, AI achievers devoted 14% of their total technology budgets to AI, while in 2021 they devoted 28%. In 2024, they plan to devote 34%. “These companies know they have only scratched the surface of their AI transformations and that the quality of their investments matters just as much as the quantity. For AI achievers, continued investment largely involves expanding the scope of AI to deliver maximum impact, while cross-pollinating AI solutions and redeploying resources in the process.”
Investments in AI are on the rise. In 2021, 19% of the surveyed companies used more than 30% of their tech budgets for AI projects, the survey shows. By 2024, the percentage of organizations investing more than 30% of their tech budgets in AI will increase to 49%. Nearly 75% of companies have integrated AI into their business strategies and reworked their cloud plans to achieve AI success, the survey also shows.
![Ready to Complete the Data Pipeline with Streaming Applications? [Visit Nstream.io]](https://flagrantmalfeasance.com/wp-content/uploads/2023/04/c1eec4e8-b352-4290-830e-19341cc05d6b.png)